Miroslav Bogdanovic

Miroslav Bogdanovic

University of Toronto

Previously:

Max Planck Institute for Intelligent Systems University of Oxford

[Google Scholar] [Contact]

Publications

Model-free Reinforcement Learning for Robust Locomotion using Demonstrations from Trajectory Optimization M. Bogdanovic, M. Khadiv, L. Righetti Frontiers in Robotics and AI, 2022. [PDF] [Video] [Project page]

Learning Variable Impedance Control for Contact Sensitive Tasks M. Bogdanovic, M. Khadiv, L. Righetti IEEE Robotics and Automation Letters (RA-L), 2020. [PDF] [Video]

An Open-Source Robot for Learning Dexterity M. Wüthrich, F. Widmaier, F. Grimminger, J. Akpo, S. Joshi, V. Agrawal, B. Hammoud, M. Khadiv, M. Bogdanovic, V. Berenz et al. Conference on Robot Learning (CoRL), 2020. [PDF] [Video] [Project page]

Learning to Explore in Motion and Interaction Tasks M. Bogdanovic, L. Righetti IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019. [PDF] [Video]

Leveraging Contact Forces for Learning to Grasp H. Merzic, M. Bogdanovic, D. Kappler, L. Righetti, J. Bohg IEEE International Conference on Robotics and Automation (ICRA), 2019. [PDF] [Video]

Deep Apprenticeship Learning for Playing Video Games M. Bogdanovic, D. Markovikj, M. Denil, N. de Freitas Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI-15), 2015. [PDF]

Model-free Reinforcement Learning for Robust Locomotion using Demonstrations from Trajectory Optimization